Skills
A collection of reusable security testing, audit, and compliance skill methodologies installable into 50+ AI agents like Claude Code, Gemini CLI, and Codex.
Rifteo · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add Rifteo/skills技能说明
Rifteo Skills
(Your agent improvises. Skills don't.) Install proven pentest methodologies into Claude Code, Gemini CLI, Codex, and 50+ other agents in one command.
The problem with AI agents and security work
Ask an agent to hunt for IDOR bugs. It will improvise. It misses verb inconsistency checks, skips GraphQL object exposure, and never tests parameter pollution. You re-prompt five times, spend 3x the tokens, and still get an incomplete result.
The agent is not dumb. It lacks a methodology.
What a skill is
A skill is a battle-tested methodology file your agent reads before starting a task. It covers every test case, every bypass technique, every output format a practitioner would use. The agent stops improvising and starts executing.
| Without skill | With skill | |
|---|---|---|
| Output quality | Inconsistent | Structured and complete |
| Turns to finish | 3 to 5 | 1 |
| Methodology coverage | Partial | Full |
| Report format | Whatever the agent guesses | Triage-ready, platform-specific |
28 skills. 53 agents. One command to install.
Benchmarks
19 skills. Real engagements. Same prompt. Same model. Measured.
| Without skill | With skill | |
|---|---|---|
| Tokens consumed | baseline |